© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9832
    Prev
    Next
    INDEX
    Explanations

    ammunition and weapon parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    庵
    -0.10
    å¤ļä½Ļ
    -0.09
    ãģĬãģĭ
    -0.09
    uko
    -0.09
    ÑĤели
    -0.08
    ETY
    -0.08
    ety
    -0.08
    ä¸ļä½Ļ
    -0.08
    ponents
    -0.08
    诿
    -0.08
    POSITIVE LOGITS
    å¼¹
    0.10
    åħħ足
    0.09
    åħħæ²Ľ
    0.09
    iras
    0.09
    UMENT
    0.09
    æĬķ身
    0.08
    秦
    0.08
    rey
    0.08
    çĽĴ
    0.08
    沸èħ¾
    0.08
    Activations Density 0.004%

    No Known Activations